AUTOASSOCIATIVE SEGMENTATION FOR REAL-TIME OBJECT RECOGNITION IN REALISTIC OUTDOOR IMAGES

As digital signal processors (DSPs) become more advanced, many real-ti me recognition problems will be solved with completely integrated solu tions, in this paper a methodology which is designed for today's DSP a rchitectures and is capable of addressing applications in real-time co lor object recognition is presented The methodology is integrated into a processing structure called raster scan video processing which requ ires a small amount of memory. The small amount of memory required ena bles the entire recognition system to be implemented on a single DSP. This autoassociative segmentation approach provides a means for desatu rated color images to be segmented. The system is applied to the probl em of stop sign recognition in realistically captured outdoor images. (C) 1998 SPIE and IS&T. [S1017-9909(98)01102-7].